Nikola Jovanović

LLM Fingerprinting via Semantically Conditioned Watermarks

Watermarking Diffusion Language Models

Watermarking Autoregressive Image Generation

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models

Black-Box Detection of Language Model Watermarks

MathConstruct: Challenging LLM Reasoning with Constructive Proofs

Ward: Provable RAG Dataset Inference via LLM Watermarks

Discovering Spoofing Attempts on Language Model Watermarks

Discovering Clues of Spoofed LM Watermarks

BaxBench: Can LLMs Generate Correct and Secure Backends?